GPLD3D: Latent Diffusion of 3D Shape Generative Models by Enforcing Geometric and Physical Priors
State-of-the-art man-made shape generative models usually adopt established generative models under a suitable implicit shape representation. A common theme is to perform distribution alignment which does not explicitly model important shape priors. As a result many synthetic shapes are not connected. Other synthetic shapes present problems of physical stability and geometric feasibility. This paper introduces a novel latent diffusion shape-generative model regularized by a quality checker that outputs a score of a latent code. The scoring function employs a learned function that provides a geometric feasibility score and a deterministic procedure to quantify a physical stability score. The key to our approach is a new diffusion procedure that combines the discrete empirical data distribution and a continuous distribution induced by the quality checker. We introduce a principled approach to determine the tradeoff parameters for learning the denoising network at different noise levels. Experimental results show that our approach outperforms state-of-the-art shape generations quantitatively and qualitatively on ShapeNet-v2.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Dreaming Smoothly and Sample Efficiently with Gradient Penalized Latent Dynamics
Model-based reinforcement learning improves sample efficiency by learning a world model. However, existing latent world models such as DreamerV3 do not explicitly enforce local smoothness in their learned transition dyna…
Reinforcement LearningContinuous ControlTopology-Aware Latent Diffusion for 3D Shape Generation
We introduce a new generative model that combines latent diffusion with persistent homology to create 3D shapes with high diversity, with a special emphasis on their topological characteristics. Our method involves repre…
3D Shape GenerationDiversityNavigate3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models
We introduce 3DShape2VecSet, a novel shape representation for neural fields designed for generative diffusion models. Our shape representation can encode 3D shapes given as surface models or point clouds, and represents …
3D Shape RepresentationPoint Cloud CompletionColor encoding in Latent Space of Stable Diffusion Models
Recent advances in diffusion-based generative models have achieved remarkable visual fidelity, yet a detailed understanding of how specific perceptual attributes - such as color and shape - are internally represented rem…
DNF: Unconditional 4D Generation with Dictionary-based Neural Fields
While remarkable success has been achieved through diffusion-based 3D generative models for shapes, 4D generative modeling remains challenging due to the complexity of object deformations over time. We propose DNF, a new…
Dictionary Learning